AVA

doi:doi:10.57702/cmlcpu52

AVA

The dataset used in this paper is a Flickr image dataset, which is used to evaluate the proposed deep aesthetic feature learning framework.

BibTex:

@dataset{Chunhui_Gu_and_Chen_Sun_and_David_A_Ross_and_Carl_Vondrick_and_Caroline_Pantofaru_and_Yeqing_Li_and_Sudheendra_Vijayanarasimhan_and_George_Toderici_and_Susanna_Ricco_and_Rahul_Sukthankar_2024,
    abstract = {The dataset used in this paper is a Flickr image dataset, which is used to evaluate the proposed deep aesthetic feature learning framework.},
    author = {Chunhui Gu and Chen Sun and David A Ross and Carl Vondrick and Caroline Pantofaru and Yeqing Li and Sudheendra Vijayanarasimhan and George Toderici and Susanna Ricco and Rahul Sukthankar},
    doi = {10.57702/cmlcpu52},
    institution = {No Organization},
    keyword = {'AVA', 'Action Recognition', 'Activity Recognition', 'Deep Learning', 'Human Action Recognition', 'Human Behavior', 'Image Classification', 'Spatial Temporal Action Detection', 'Spatiotemporal Analysis', 'Video Analysis', 'action recognition', 'human action', 'video dataset', 'video recognition'},
    month = {dec},
    publisher = {TIB},
    title = {AVA},
    url = {https://service.tib.eu/ldmservice/dataset/ava},
    year = {2024}
}